The Used Car Price Prediction dataset contains 4,009 vehicle listings collected from the automotive marketplace cars.com. Each row represents a unique car and includes nine key attributes relevant to pricing and vehicle characteristics. Dataset is taken from Kaggle: https://www.kaggle.com/datasets/taeefnajib/used-car-price-prediction-dataset
The dataset provides information on:
Brand and model – manufacturer and specific vehicle model
Model year – age of the car, influencing depreciation
Mileage – an indicator of usage and wear
Fuel type – e.g., gasoline, diesel, electric, hybrid
Engine type – performance and efficiency characteristics
Transmission – automatic or manual
Exterior/interior colors – aesthetic properties
Accident history – whether the car has previously been damaged
Clean title – legal/ownership status
Price – listed price of the vehicle
Overall, the dataset offers a structured overview of key features that influence used car valuation. It is well-suited for analytical tasks such as understanding pricing drivers, exploring consumer preferences, and building predictive models for vehicle prices. # Raw data
We load the original CSV directly from the project data folder using
here() so paths work regardless of the working
directory.
raw_path <- here("data", "raw", "used_cars.csv")
cars_raw <- readr::read_csv(raw_path, show_col_types = FALSE)
Basic structure and summary statistics of the raw dataset:
glimpse(cars_raw)
## Rows: 4,009
## Columns: 12
## $ brand <chr> "Ford", "Hyundai", "Lexus", "INFINITI", "Audi", "Acura", ~
## $ model <chr> "Utility Police Interceptor Base", "Palisade SEL", "RX 35~
## $ model_year <dbl> 2013, 2021, 2022, 2015, 2021, 2016, 2017, 2001, 2021, 202~
## $ milage <chr> "51,000 mi.", "34,742 mi.", "22,372 mi.", "88,900 mi.", "~
## $ fuel_type <chr> "E85 Flex Fuel", "Gasoline", "Gasoline", "Hybrid", "Gasol~
## $ engine <chr> "300.0HP 3.7L V6 Cylinder Engine Flex Fuel Capability", "~
## $ transmission <chr> "6-Speed A/T", "8-Speed Automatic", "Automatic", "7-Speed~
## $ ext_col <chr> "Black", "Moonlight Cloud", "Blue", "Black", "Glacier Whi~
## $ int_col <chr> "Black", "Gray", "Black", "Black", "Black", "Ebony.", "Bl~
## $ accident <chr> "At least 1 accident or damage reported", "At least 1 acc~
## $ clean_title <chr> "Yes", "Yes", NA, "Yes", NA, NA, "Yes", "Yes", "Yes", "Ye~
## $ price <chr> "$10,300", "$38,005", "$54,598", "$15,500", "$34,999", "$~
We base the EDA on the engineered dataset
(data/processed/used_cars_features.csv) that keeps cleaned
numeric fields and derived features like age, mileage in thousands, and
accident flags.
features_path <- here("data", "processed", "used_cars_features.csv")
cars <- readr::read_delim(features_path, delim = ";", show_col_types = FALSE)
| variable | median | mean | p25 | p75 | sd | min | max |
|---|---|---|---|---|---|---|---|
| price_dollar | 28000.00 | 36865.68 | 15500.00 | 46999.00 | 36531.16 | 2000.0 | 649999.00 |
| log_price | 10.24 | 10.19 | 9.65 | 10.76 | 0.82 | 7.6 | 13.38 |
| age | 9.00 | 10.32 | 6.00 | 14.00 | 5.87 | 1.0 | 29.00 |
| milage_k | 63.00 | 72.14 | 30.00 | 103.00 | 53.60 | 0.0 | 405.00 |
| horsepower | 310.00 | 331.51 | 248.00 | 400.00 | 120.32 | 76.0 | 1020.00 |
| accident | n | share |
|---|---|---|
| At least 1 accident or damage reported | 871 | 0.28 |
| None reported | 2194 | 0.72 |
Median listing sits around $28k, with the middle 50% between roughly $15.5k and $47k, while the maximum reaches $650k—explaining the heavy right tail. Median age is 9 years (IQR: 6–14), typical mileage is about 63k miles (IQR: 30k–103k), and horsepower clusters around 310 HP (IQR: 248–400). About 28% of cars report an accident or damage, a meaningful factor for pricing.
Raw prices are extremely right-skewed, with most listings below $80k but a long tail of luxury and exotic vehicles. Modeling on this scale would be dominated by a few high-price outliers.
Log transformation produces a more bell-shaped distribution and stabilizes variance, making linear-style models and visual comparisons more reliable.
Prices decline with age across fuels. Electric listings start high but show the sharpest early drop; diesel holds comparatively high prices across ages (though the diesel sample is small), and gasoline sits lower overall.
Among the 12 most common brands, Porsche leads on median price, followed by Land Rover and Mercedes-Benz; Volume brands (Toyota, Nissan, Jeep) cluster lower with tighter spreads, while some (Chevrolet, Ford) span broader lineups.
Higher mileage correlates with lower prices. We use a loess smoother (not a straight trendline) and cap the x-axis at 250k miles to reduce the influence of extreme outliers; automatics show a steady decline, and the smaller manual subset is noisier but similar in direction.
Cars with reported accidents trade at a clear discount relative to clean histories, even after log-scaling prices, confirming accident history as an important predictor.
We fit radial-kernel SVM regressors on log_price using
both e1071::svm and kernlab (via
caret::train). Both models use the same 80/20 train-test
split; hyperparameters are tuned by cross-validation and evaluated on
the hold-out test set below.
svm_metrics <- readr::read_csv(
here("report", "models", "svm", "svm_log_price_metrics.csv"),
show_col_types = FALSE
)
svm_best <- readr::read_lines(here("report", "models", "svm", "svm_best_model.txt"))[1]
svm_metrics_wide <- svm_metrics |>
tidyr::pivot_wider(names_from = .metric, values_from = .estimate)
knitr::kable(svm_metrics_wide, digits = 3, caption = "Test metrics for SVM variants (target: log_price)")
| .estimator | model | rmse | mae | rsq |
|---|---|---|---|---|
| standard | e1071_radial | 0.290 | 0.209 | 0.868 |
| standard | kernlab_radial | 0.354 | 0.251 | 0.803 |
The e1071 radial SVM is best by RMSE (~0.290) and R²
(~0.868), outperforming the kernlab variant on this split. SVMs do not
yield straightforward coefficient interpretations; they learn support
vectors and decision functions in a transformed feature space. To
understand feature effects you would rely on downstream tools (e.g.,
partial dependence or SHAP), but within this report we focus on
comparative error metrics and note that the tuned radial kernel captures
non-linear relationships beyond the linear/log models.
Cross-validation setup: both SVMs were tuned with 3-fold cross
validation on the training set (same 80/20 split for both).
e1071::tune() searched a compact grid of cost
and gamma; caret::train(method = "svmRadial")
searched a grid of C and sigma. Final metrics
shown above are from the untouched test set, so cross validation was
only for hyperparameter selection.
Best model: e1071_radial with RMSE = 0.2898 (lower is better)
Two regressors on log_price: a caret nnet
(with dummying + scaling, 3-fold cross validation over size/decay) and a
manual neuralnet (shallow hidden layer). Metrics below come
from the test split; cross validation was used only for tuning.
nn_metrics <- readr::read_csv(
here("report", "models", "nn", "nn_log_price_metrics.csv"),
show_col_types = FALSE
)
nn_best <- readr::read_lines(here("report", "models", "nn", "nn_best_model.txt"))[1]
nn_metrics_wide <- nn_metrics |>
tidyr::pivot_wider(names_from = .metric, values_from = .estimate)
knitr::kable(nn_metrics_wide, digits = 3, caption = "Test metrics for NN variants (target: log_price)")
| .estimator | model | rmse | mae | rsq |
|---|---|---|---|---|
| standard | caret_nnet | 0.369 | 0.265 | 0.791 |
| standard | neuralnet_manual | 0.408 | 0.285 | 0.743 |
Best NN model: caret_nnet with RMSE = 0.369 (lower is better) — the
manual neuralnet edge is small (RMSE ≈ 0.388 vs. 0.392), so
both nets are in a similar error band; the manual net slightly reduces
bias on the high end (see fewer large positive residuals).